Manhattan
mn_output
# How many EDs in Manhattan
mn_output$ED %>% unique() %>% length()
## [1] 1478
# How many Microfilms in Manhattan
mn_output$microfilm %>% unique() %>% length()
## [1] 1276
# How many unique Street Names in Manhattan
mn_output$street_add %>% unique() %>% length()
## [1] 8557
# Street Names
mn_output$best_match %>% unique() %>% head(200)
## [1] "FERRY" "DUANE" "FRANKFORT"
## [4] "WILLIAM" "ROSE" "N WILLIAM"
## [7] "NEW CHAMBERS" "PARK ROW" "GOLD"
## [10] "PEARL" "HAGUE" "VANDEWATER"
## [13] "OAK" "CHENUT" "NEW BOWERY"
## [16] "CHENUT ST" "CHAMBERS" "BATAVIA"
## [19] "ROOSEVELT" "CHERRY" "WATER"
## [22] NA "PECK SLIP" "DOVER"
## [25] "FRONT" "SOUTH" "MADISON"
## [28] "JAMES" "OLIVER" "CATHERINE"
## [31] "HENRY" "CHATHAM SQUARE" "BROADWAY E"
## [34] "JAMES SLIP" "CATHERINE SLIP" "CITY HALL PL"
## [37] "REPUBLICAN ALY" "BROADWAY" "CARDINAL"
## [40] "CITY HALL PARK" "WALKER" "LEONARD"
## [43] "WORTH" "CENTRE" "FRANKLIN"
## [46] "LAFAYETTE" "WHITE" "BAXTER"
## [49] "CANAL" "PARK" "MULBERRY"
## [52] "MOTT" "PELL" "DOYERS"
## [55] "BOWERY" "BAYARD" "ELIZABETH"
## [58] "BARROW" "COMMERCE" "BEDFORD"
## [61] "4 W" "JONES" "BLEECKER"
## [64] "CORNELIA" "W 4" "MORTON"
## [67] "LEROY" "HUDSON" "LUKE\\'S PL"
## [70] "CARMINE" "CLARKSON" "VARICK"
## [73] "W HOUON ST" "DOWNING" "1 AVE"
## [76] "99 E" "E 99" "FIR AVE"
## [79] "2 AVE" "100 E" "E 100"
## [82] "3 AVE" "101 E" "98 E"
## [85] "E 98" "97 E" "E 97"
## [88] "E 96" "96 E" "E 95"
## [91] "E 94" "95 E" "94 E"
## [94] "E 93" "93 E" "92 E"
## [97] "91 E" "90 E" "E 90"
## [100] "E 92" "E 91" "E 89"
## [103] "89 E" "88 E" "E 88"
## [106] "E 87" "87 E" "86 E"
## [109] "E 86" "LEXINGTON AVE" "PARK AVE"
## [112] "LEX AVE" "MADISON AVE" "E 98"
## [115] "5 AVE" "W 112" "LENOX AVE"
## [118] "W 111" "111 W" "112 W"
## [121] "W 113" "113 W" "114 W"
## [124] "E 114" "115 W" "W 115"
## [127] "W 116" "116 W" "W 117"
## [130] "117 W" "W 118" "118 W"
## [133] "W 119" "119 W" "W 120"
## [136] "W 121" "MT MORRIS AVE" "123 W"
## [139] "MT MORRIS PL" "124 W" "W 126"
## [142] "126 W" "W 124" "W 125"
## [145] "125 W" "128 W" "127 W"
## [148] "W 127" "W 129" "W 128"
## [151] "129 W" "130 W" "131 W"
## [154] "W 130" "W 131" "132 W"
## [157] "W 132" "W 133" "133 W"
## [160] "DYCKMAN" "W 205" "W 206"
## [163] "209 W" "213 W" "0"
## [166] "W 215" "W 216" "HARLEM RIVER"
## [169] "228 W" "227 W" "CHARLES PL"
## [172] "MARBLE HL AVE" "W 218" "9 AVE"
## [175] "225 W" "VAN CORLEAR PL" "FORT CHARLES PL E"
## [178] "ADRIAN PL" "TER VIEW AVE" "219 W"
## [181] "SHERMAN AVE" "BOLTON RD" "SEAMAN AVE"
## [184] "PRESCOTT AVE" "HAWTHORNE" "COOPER"
## [187] "ACADEMY" "W 213" "10 AVE"
## [190] "BEAK" "EMERSON" "BENNETT AVE"
## [193] "NAGLE AVE" "B" "C"
## [196] "NORTH RIVER" "FORT WASHINGTON AVE" "NORTHERN AVE"
## [199] "W 187" "NICHOLAS AVE"
# Total number of entries from sample dataset in Manhattan
nrow(mn_output)
## [1] 557357
# Tabulate Result Type in Manhattan
# 1 of 6 possible match types: (1) Perfect Match, (2) Identical Match, (3) Singular Mode, (4) Multiple Modes, (5) NA mode, (6) No match. Refer to documentation for more details.
table(mn_output$result_type)
##
## 1 2 3 4 5 6
## 155740 70290 265278 18236 6713 2863
- 28% Perfect Match
- 12% Identical Match
- 47.5% Singular Mode
- 3% Multiple Modes
- 1.2% NAs
- 0.5% No Match
# NAs
mn_output %>% filter(result_type == 5) %>%
select(ED, street_add, best_match, result_type) %>%
head(200)
# No Outputs -- the best match comes out as "0"
mn_output %>% filter(result_type == 6) %>%
select(ED, street_add, best_match, result_type) %>%
head(200)
# Tabulate Flagged Streets in Manhattan
table(mn_output$flag_st)
##
## 0 1
## 491308 27812
# Tabulate Flagged House Number Cleaned in Manhattan
table(mn_output$flag_hn_cleaned)
##
## 0 1
## 152319 7350
# Tabulate Flagged Filled House Numbers in Manhattan
table(mn_output$flg_filled_hn)
##
## 0 1
## 192627 364730
Brooklyn
bk_output
# How many EDs in Brooklyn
bk_output$ED %>% unique() %>% length()
## [1] 1106
# How many Microfilms in Brooklyn
bk_output$microfilm %>% unique() %>% length()
## [1] 1527
# How many unique Street Names in Brooklyn
bk_output$street_add %>% unique() %>% length()
## [1] 7076
# Street Names Brooklyn
bk_output$best_match %>% unique() %>% head(200)
## [1] "MARION" "HOWARD AVE" "CHAUNCEY"
## [4] "RALPH AVE" "BAINBRIDGE" "SARATOGA AVE"
## [7] "SUMPTER" NA "MCDOUGAL"
## [10] "FULTON" "HULL" "HERKIMER"
## [13] "ATLANTIC AVE" "BANCROFT PL" "PRESCOTT PL"
## [16] "DEWEY PL" "LOUIS PL" "RUSSELL PL"
## [19] "OCEAN PL" "HOPKINSON AVE" "GUNTHER PL"
## [22] "ROCKAWAY AVE" "SOMERS" "BROADWAY"
## [25] "1 AVE" "TRUXTON" "EAERN PKWY"
## [28] "EA PKWY" "PLEASANT PL" "SACKMAN"
## [31] "NORMAN PL" "JARDINE PL" "SHERLOCK PL"
## [34] "VAN SINDEREN AVE" "HAVENS PL" "CONWAY"
## [37] "WILLIAMS PL" "E NEW YORK AVE" "ROGERS AVE"
## [40] "BEDFORD AVE" "MARKS AVE" "FRANKLIN AVE"
## [43] "BERGEN" "DEAN" "PACIFIC"
## [46] "PROSPECT PL" "PARK PL" "NORAND AVE"
## [49] "GRANT SQ" "NEW YORK AVE" "BROOKLYN AVE"
## [52] "KINGON AVE" "ALBANY AVE" "REVERE PL"
## [55] "SAINT MARK'S AVE" "TROY AVE" "SCHENECTADY AVE"
## [58] "UTICA AVE" "ROCHEER AVE" "BUFFALO AVE"
## [61] "ETNA" "RICHMOND" "RIDGEWOOD AVE"
## [64] "LOGAN" "CHENUT ST" "EUCLID AVE"
## [67] "PINE" "CRESCENT" "GRANT AVE"
## [70] "ENFIELD" "NICHOLS AVE" "LINCOLN AVE"
## [73] "RAILROAD AVE" "HEMLOCK" "ELDERTS LN"
## [76] "CRESCENT TER" "GLEN" "WELDON"
## [79] "SHERIDAN AVE" "WEIRFIELD" "9 AVE"
## [82] "FORCE TUBE AVE" "ARLINGTON AVE" "DRESDEN"
## [85] "HALE AVE" "NORWOOD AVE" "GLENMORE AVE"
## [88] "LIBERTY AVE" "FOUNTAIN AVE" "MILFORD"
## [91] "MONTAUK AVE" "BERRIMAN" "HL"
## [94] "MAGENTA" "CRYAL ST" "AUTUMN AVE"
## [97] "DOSCHER" "CRYAL" "FORBELL AVE"
## [100] "MCKINLEY AVE" "PITKIN AVE" "ATKINS AVE"
## [103] "BELMONT AVE" "SUTTER AVE" "BLAKE AVE"
## [106] "DUMONT AVE" "VIENNA AVE" "HEGEMAN AVE"
## [109] "NEW LOTS RD" "ANLEY AVE" "WORTMAN AVE"
## [112] "SCHENCK AVE" "BARBEY" "JEROME"
## [115] "ASHFORD" "CLEVELAND" "ELTON"
## [118] "ESSEX" "SCHENK AVE" "HENDRIX"
## [121] "NEWJERSEY AVE" "PENNSYLVANIA AVE" "SHEFFIELD AVE"
## [124] "0" "MALTA" "LOUISIANA AVE"
## [127] "WILLIAMS AVE" "SNEDIKER AVE" "SUMNER PL"
## [130] "FLUSHING AVE" "FAYETTE" "BEAVER"
## [133] "ELLERY" "BELVIDERE" "LOCU ST"
## [136] "PARK" "ARION PL" "BUSHWICK AVE"
## [139] "MELROSE" "JEFFERSON" "TROUTMAN"
## [142] "MYRTLE AVE" "GARDEN" "BREMEN"
## [145] "MONTIETH" "NOLL" "EVERGREEN AVE"
## [148] "FORRE ST" "WILLOUGHBY AVE" "CHARLES PL"
## [151] "DITMARS" "SUYDAM" "HART"
## [154] "DODWORTH" "LAWTON" "CEDAR"
## [157] "KOSCIUSKO" "DE KALB AVE" "CENTRAL AVE"
## [160] "HAMBURG AVE" "ANHOPE ST" "OCKHOLM ST"
## [163] "ARR ST" "KOSSUTH PL" "LAFAYETTE AVE"
## [166] "VAN BUREN" "HARMAN" "HIMROD"
## [169] "GREENE AVE" "BLEECKER" "GEORGE"
## [172] "FORRE" "KNICKERBOCKER AVE" "IRVING AVE"
## [175] "OCKHOLM" "WYCKOFF AVE" "NICHOLAS AVE"
## [178] "CYPRESS AVE" "SCOTT AVE" "ANHOPE"
## [181] "GROVE" "CENTRAL PL" "RALPH"
## [184] "LINDEN" "GATES AVE" "PALMETTO"
## [187] "WOODBINE" "MADISON" "RIDGEWOOD PL"
## [190] "HALSEY" "CORNELIA" "JEFFERSON AVE"
## [193] "PUTNAM AVE" "HANCOCK" "ELDERT"
## [196] "COVERT" "SCHAEFFER" "CONEY ISLAND AVE"
## [199] "R AVE" "14 E"
# Total number of entries from sample dataset in Brooklyn
nrow(bk_output)
## [1] 371833
# Tabulate Result Type in Brooklyn
# 1 of 6 possible match types: (1) Perfect Match, (2) Identical Match, (3) Singular Mode, (4) Multiple Modes, (5) NA mode, (6) No match. Refer to documentation for more details.
table(bk_output$result_type)
##
## 1 2 3 4 5 6
## 284604 29726 35184 5701 4992 3164
- 76.5% Perfect Match
- 7.9% Identical Match
- 9.5% Singular Mode
- 1.5% Multiple Modes
- 1.3% NAs
- 0.8% No Match
# Tabulate Flagged Streets in Brooklyn
table(bk_output$flag_st)
##
## 0 1
## 349514 13857
# Tabulate Flagged House Number Cleaned in Brooklyn
table(bk_output$flag_hn_cleaned)
##
## 0 1
## 176736 2567
# Tabulate Flagged Filled House Numbers in Brooklyn
table(bk_output$flg_filled_hn)
##
## 0 1
## 188898 182935